Comprehensive Qwirkle RL agent application. We'll use Monte Carlo Tree Search (MCTS) combined with Q-Learning - the best approaches for tile-placement games with high branching factors.
reinforcement-learning deep-reinforcement-learning q-learning game-theory monte-carlo-tree-search combinatorial-game-theory multi-agent-rl tile-placement-games
-
Updated
Dec 14, 2025 - Python